Model trained on the TinyStories Dataset, see https://arxiv.org/abs/2305.07759
------ EXAMPLE USAGE ---
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
model = AutoModelForCausalLM.from_pretrained('roneneldan/TinyStories-3M')
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")
prompt = "Once upon a time there was"
input_ids = tokenizer.encode(prompt, return_tensors="pt")
Generate completion
output = model.generate(input_ids, max_length = 1000, num_beams=1)
Decode the completion
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
Print the generated text
print(output_text)
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 24.18 |
| ARC (25-shot) | 22.01 |
| HellaSwag (10-shot) | 25.58 |
| MMLU (5-shot) | 24.99 |
| TruthfulQA (0-shot) | 47.33 |
| Winogrande (5-shot) | 49.25 |
| GSM8K (5-shot) | 0.0 |
| DROP (3-shot) | 0.1 |